Machine Learning For Beamline Steering

TL;DR

This paper explores using deep neural networks to automate and improve the calibration process of beam steering in particle accelerators, aiming to reduce human effort and increase efficiency.

Contribution

It introduces a deep learning approach trained on archival data to assist in beamline calibration, demonstrating potential to outperform human operators.

Findings

Deep learning models achieve comparable or better calibration accuracy than humans.

Models trained on archival data generalize well to simulation data.

Potential to automate beam steering calibration, reducing operator workload.

Abstract

Beam steering is the process involving the calibration of the angle and position at which a particle accelerator's electron beam is incident upon the x-ray target with respect to the rotation axis of the collimator. Beam Steering is an essential task for light sources. In the case under study, the LINAC To Undulator (LTU) section of the beamline is difficult to aim. Each use of the accelerator requires re-calibration of the magnets in this section. This involves a substantial amount of time and effort from human operators, while reducing scientific throughput of the light source. We investigate the use of deep neural networks to assist in this task. The deep learning models are trained on archival data and then validated on simulation data. The performance of the deep learning model is contrasted against that of trained human operators.